From 5993177ae352bd6194eb8fe569b0505ea46c6111 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Mon, 4 May 2015 14:57:47 +0200
Subject: [PATCH] [4chan] more metadata entries (size, width, height)

---
 gallery_dl/extractor/4chan.py | 34 +++++++++++++++++++---------------
 1 file changed, 19 insertions(+), 15 deletions(-)

diff --git a/gallery_dl/extractor/4chan.py b/gallery_dl/extractor/4chan.py
index bc23ed3e..7d6c826b 100644
--- a/gallery_dl/extractor/4chan.py
+++ b/gallery_dl/extractor/4chan.py
@@ -18,51 +18,55 @@ info = {
     "directory": ["{category}", "{board}-{thread-id}"],
     "filename": "{timestamp}-{name}",
     "pattern": [
-        r"(?:https?://)?boards\.4chan\.org/([^/]+)/thread/(\d+)(?:/([^#]*))?",
+        r"(?:https?://)?boards\.4chan\.org/([^/]+)/thread/(\d+).*",
     ],
 }
 
 class FourChanExtractor(SequentialExtractor):
 
-    url_fmt = "https://boards.4chan.org/{board}/res/{thread-id}.html"
+    url_fmt = "https://boards.4chan.org/{0}/res/{1}.html"
     regex = (
-        r'<a href="(//i.4cdn.org/[^/]+/(\d+)\.([^"]+))"'
-        r' target="_blank">([^<]+)</a>'
+        r'<a (?:title="(?P<orig_name>[^"]+)" )?href="'
+        r'(?P<url>//i.4cdn.org/[^/]+/(?P<timestamp>\d+)\.(?P<extension>[^"]+))'
+        r'" target="_blank">(?P<name>[^<]+)</a> '
+        r'\((?P<size>[^,]+), (?P<width>\d+)x(?P<height>\d+)\)'
     )
 
     def __init__(self, match, config):
         SequentialExtractor.__init__(self, config)
-        self.metadata = self.get_job_metadata(match)
+        self.match = match
+        self.metadata = None
 
     def items(self):
         yield Message.Version, 1
-        yield Message.Directory, self.metadata
 
-        url = self.url_fmt.format(**self.metadata)
+        url = self.url_fmt.format(*self.match.groups())
         text = self.request(url).text
+        self.metadata = self.get_job_metadata(text)
+
+        yield Message.Directory, self.metadata
         for match in re.finditer(self.regex, text):
             yield Message.Url, self.get_file_url(match), self.get_file_metadata(match)
 
-    @staticmethod
-    def get_job_metadata(match):
+    def get_job_metadata(self, text):
         """Collect metadata for extractor-job"""
-        board, thread_id, title = match.groups()
+        board, thread_id = self.match.groups()
+        title, _ = self.extract(text, '"description" content="', ' - &quot;/')
         return {
             "category": info["category"],
             "board": board,
             "thread-id": thread_id,
-            "title": title,
+            "title": unquote(title),
         }
 
     def get_file_metadata(self, match):
         """Collect metadata for a downloadable file"""
         data = self.metadata
-        data["timestamp"] = match.group(2)
-        data["extension"] = match.group(3)
-        data["name"] = unquote(match.group(4))
+        data.update(match.groupdict(default=""))
+        data["name"] = unquote(data["orig_name"] or data["name"])
         return data
 
     @staticmethod
     def get_file_url(match):
         """Extract download-url from 'match'"""
-        return "https:" + match.group(1)
+        return "https:" + match.group("url")